Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    renovation and updates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Report
    -0.07
     INTERRU
    -0.06
    ें।
    -0.06
    улю
    -0.06
    oks
    -0.06
    се
    -0.06
    Clipboard
    -0.06
    yles
    -0.06
    Factory
    -0.06
    Dom
    -0.06
    POSITIVE LOGITS
     sonucu
    0.07
     英语
    0.07
    ็อต
    0.06
     tỷ
    0.06
     došlo
    0.06
    ormsg
    0.06
     mud
    0.06
     φω
    0.06
     �
    0.06
     хозяй
    0.06
    Act Density 0.148%

    No Known Activations